# Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation

arXiv: https://arxiv.org/abs/2311.12028 · HTML: https://mlsanity.com/paper/2311.12028/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 59 references that are in the map.
- First posted on arXiv 20 Nov 2023.

## Builds on (most cited first, 30 of 43)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop](https://mlsanity.com/paper/1909.12828/) (2019)
- [Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision](https://mlsanity.com/paper/1611.09813/) (2016)
- [3D human pose estimation in video with temporal convolutions and semi-supervised training](https://mlsanity.com/paper/1811.11742/) (2018)
- [A simple yet effective baseline for 3d human pose estimation](https://mlsanity.com/paper/1705.03098/) (2017)
- [Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations](https://mlsanity.com/paper/2202.07800/) (2022)
- [AdaViT: Adaptive Tokens for Efficient Vision Transformer](https://mlsanity.com/paper/2112.07658/) (2021)
- [PARE: Part Attention Regressor for 3D Human Body Estimation](https://mlsanity.com/paper/2104.08527/) (2021)
- [3D Human Pose Estimation with Spatial and Temporal Transformers](https://mlsanity.com/paper/2103.10455/) (2021)
- [Semantic Graph Convolutional Networks for 3D Human Pose Regression](https://mlsanity.com/paper/1904.03345/) (2019)
- [MotionBERT: A Unified Perspective on Learning Human Motion Representations](https://mlsanity.com/paper/2210.06551/) (2022)
- [Adaptive Token Sampling For Efficient Vision Transformers](https://mlsanity.com/paper/2111.15667/) (2021)
- [SPViT: Enabling Faster Vision Transformers via Soft Token Pruning](https://mlsanity.com/paper/2112.13890/) (2021)
- [MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video](https://mlsanity.com/paper/2203.00859/) (2022)
- [MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation](https://mlsanity.com/paper/2111.12707/) (2021)
- [Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer](https://mlsanity.com/paper/2204.08680/) (2022)
- [SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach](https://mlsanity.com/paper/2007.09389/) (2020)
- [Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimation](https://mlsanity.com/paper/2103.14304/) (2021)
- [PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation](https://mlsanity.com/paper/2303.17472/) (2023)
- [PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation](https://mlsanity.com/paper/2105.02465/) (2021)
- [Motion Guided 3D Pose Estimation from Videos](https://mlsanity.com/paper/2004.13985/) (2020)
- [Cascaded deep monocular 3D human pose estimation with evolutionary training data](https://mlsanity.com/paper/2006.07778/) (2020)
- [P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimation](https://mlsanity.com/paper/2203.07628/) (2022)
- [Token Pooling in Vision Transformers](https://mlsanity.com/paper/2110.03860/) (2021)
- [KVT: k-NN Attention for Boosting Vision Transformers](https://mlsanity.com/paper/2106.00515/) (2021)
- [Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation](https://mlsanity.com/paper/2108.07181/) (2021)
- [Conditional Directed Graph Convolution for 3D Human Pose Estimation](https://mlsanity.com/paper/2107.07797/) (2021)
- [Beyond Attentive Tokens: Incorporating Token Importance and Diversity for Efficient Vision Transformers](https://mlsanity.com/paper/2211.11315/) (2022)

## Built on by (most cited first, 15 of 15)

- [Towards Balanced Multi-Modal Learning in 3D Human Pose Estimation](https://mlsanity.com/paper/2501.05264/) (2025)
- [Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning](https://mlsanity.com/paper/2508.10897/) (2025)
- [NanoHTNet: Nano Human Topology Network for Efficient 3D Human Pose Estimation](https://mlsanity.com/paper/2501.15763/) (2025)
- [Mamba-Driven Topology Fusion for Monocular 3D Human Pose Estimation](https://mlsanity.com/paper/2505.20611/) (2025)
- [FastDDHPose: Towards Unified, Efficient, and Disentangled 3D Human Pose Estimation](https://mlsanity.com/paper/2512.14162/) (2025)
- [MuPPet: Multi-person 2D-to-3D Pose Lifting](https://mlsanity.com/paper/2604.09715/) (2026)
- [Spectral Compression Transformer with Line Pose Graph for Monocular 3D Human Pose Estimation](https://mlsanity.com/paper/2505.21309/) (2025)
- [Heatmap Pooling Network for Action Recognition from RGB Videos](https://mlsanity.com/paper/2512.03837/) (2025)
- [STS-Mixer: Spatio-Temporal-Spectral Mixer for 4D Point Cloud Video Understanding](https://mlsanity.com/paper/2604.11637/) (2026)
- [DLM-VMTL:A Double Layer Mapper for heterogeneous data video Multi-task prompt learning](https://mlsanity.com/paper/2408.16195/) (2024)
- [PRGCN: A Graph Memory Network for Cross-Sequence Pattern Reuse in 3D Human Pose Estimation](https://mlsanity.com/paper/2510.19475/) (2025)
- [PoseMoE: Mixture-of-Experts Network for Monocular 3D Human Pose Estimation](https://mlsanity.com/paper/2512.16494/) (2025)
- [EgoPoseVR: Spatiotemporal Multi-Modal Reasoning for Egocentric Full-Body Pose in Virtual Reality](https://mlsanity.com/paper/2602.05590/) (2026)
- [MoPO: Incorporating Motion Prior for Occluded Human Mesh Recovery](https://mlsanity.com/paper/2605.09856/) (2026)
- [HYPERPOSE: Hyperbolic Kinematic Phase-Space Attention for 3D Human Pose Estimation](https://mlsanity.com/paper/2605.10100/) (2026)

## Abstract (arXiv)

Transformers have been successfully applied in the field of video-based 3D human pose estimation. However, the high computational costs of these video pose transformers (VPTs) make them impractical on resource-constrained devices. In this paper, we present a plug-and-play pruning-and-recovering framework, called Hourglass Tokenizer (HoT), for efficient transformer-based 3D human pose estimation from videos. Our HoT begins with pruning pose tokens of redundant frames and ends with recovering full-length tokens, resulting in a few pose tokens in the intermediate transformer blocks and thus improving the model efficiency. To effectively achieve this, we propose a token pruning cluster (TPC) that dynamically selects a few representative tokens with high semantic diversity while eliminating the redundancy of video frames. In addition, we develop a token recovering attention (TRA) to restore the detailed spatio-temporal information based on the selected tokens, thereby expanding the network output to the original full-length temporal resolution for fast inference. Extensive experiments on two benchmark datasets (i.e., Human3.6M and MPI-INF-3DHP) demonstrate that our method can achieve both high efficiency and estimation accuracy compared to the original VPT models. For instance, applying to MotionBERT and MixSTE on Human3.6M, our HoT can save nearly 50% FLOPs without sacrificing accuracy and nearly 40% FLOPs with only 0.2% accuracy drop, respectively. Code and models are available at https://github.com/NationalGAILab/HoT.